mimo-v2.5-tts (Preset Voice Speech Synthesis)

Actual API Endpoint: POST https://api.tokenhot.ai/v1/chat/completions

Model Code: mimo-v2.5-tts

Synthesize speech using built-in preset voices (text-to-speech). Multiple Chinese and English voices are available out of the box, no extra configuration needed.

The text to synthesize goes in the role: assistant message; the role: user message is an optional style/tone instruction.

Supports both natural language control (in the user message) and audio tag control (embedded in the assistant message text) for style.

Supports singing mode (add the (唱歌) tag at the beginning of the assistant message text).

Supports both non-streaming (wav) and streaming (pcm16, 24kHz PCM16LE mono) output formats.

Voice design and voice cloning are not supported by this model. Use mimo-v2.5-tts-voicedesign or mimo-v2.5-tts-voiceclone for those features.

Preset Voice List:

Voice ID	Language	Gender
mimo_default	Varies by cluster (China cluster defaults to 冰糖, others default to Mia)	—
冰糖	Chinese	Female
茉莉	Chinese	Female
苏打	Chinese	Male
白桦	Chinese	Male
Mia	English	Female
Chloe	English	Female
Milo	English	Male
Dean	English	Male

Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

curl --location 'https://api.tokenhot.ai/v1/chat/completions' \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data '{ "model": "mimo-v2.5-tts", "messages": [ { "role": "user", "content": "用温柔的语气说一段晚安问候" }, { "role": "assistant", "content": "晚安，今天辛苦了，好好休息，明天又是美好的一天。" } ], "audio": { "format": "wav", "voice": "冰糖" } }'

{ "id": "chatcmpl-abc123def456", "object": "chat.completion", "created": 1774324467, "model": "mimo-v2.5-tts", "choices": [ { "index": 0, "message": { "role": "assistant", "audio": { "id": "3864a4690d8a4aaea5f6acf4853a0600", "data": "UklGR...(Base64-encoded audio data)", "expires_at": null, "transcript": null } }, "finish_reason": "stop" } ] }

mimo-v2.5-tts (Preset Voice Speech Synthesis)

Request

Responses